metadata
library_name: transformers
tags:
- unsloth
- trl
- sft
- o1
- qwen2.5
- qwen
- conversational
pipeline_tag: text-generation
license: apache-2.0
language:
- en
base_model:
- Pinkstack/PARM-V1.5-base-QwQ-Qwen-2.5-o1-3B-VLLM
Highly advanced based model for training:
- Sequence Length: 131072
- Parm 2 ultra: trained for 2 hours on 1 Million OpenO1 chats, 180k sonnet 3.5, 130k qwq messages.